https://irjet.net/archives/V4/i8/IRJET-V4I8338.pdf

1. International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 04 Issue: 08 | Aug -2017 www.irjet.net p-ISSN: 2395-0072
© 2017, IRJET | Impact Factor value: 5.181 | ISO 9001:2008 Certified Journal | Page 1891
“SYSTEM BASED MINING FOR DISCOVERING HUMAN INTERACTION IN
MEETINGS”
G. Vinitha Sanchez1, T.S. Vishnu Priya2
1M.tech,Department of Communication Systems, Sastra University,Thanjavur,India
2M.tech, Department of Communication Systems, Sastra University,Thanjavur,India
---------------------------------------------------------------------***----------------------------------------------------------------
Abstract - Human Interaction playsavitalroletounderstand
the communicative information. Understanding human
behavior is essential in applications including automated
surveillance, video archival/retrieval, medical diagnosis, and
human-computer interaction. The advent of smart meeting
that automatically records a meeting and analyzes the
generated audio-visualcontentforfutureviewing.Whilemost
of current smart meeting systems analyze the meeting
content for understanding what conclusion was made, it is
more interesting and important to know how a conclusion
was made.
Key Words: Human Interaction, Behaviour, Meeting,
Content, information
1. INTRODUCTION
Human interaction plays an important role in
understandingthiscommunicativeinformationanddifferent
from physical interactions (e.g. turn-taking andaddressing),
the human interactions here aredefinedasbehaviorsamong
meeting participants with respect to the Current topic, such
as proposing an idea, giving some comments, expressing
positive opinion, and requesting information. When
incorporated with semantics (i.e. user intention or attitude
towards a topic), interactions are more meaningful in
understanding conclusion drawing and meeting
organization.
1.1 Existing Method
Generally in meetings, human interaction plays a major
role and has much attracted in the field of image analysis
and computer vision, speech processing. Here the existing
method only analyze and visualize the human interaction
while the proposed method focus much on the
understanding of the human interaction with higher level
knowledge.
Disadvantages of existing method:
 System is complex to handle
 Identification of negative points during
meetings in the presented topic is very difficult
 This system increases the data to be repeated.
1.2 Proposed Method
Here in this paper we propose a method called mining
method in order to extract the frequent patterns of human
interaction .this frequent pattern is extracted based on the
content that is captured during face-face interaction.Also,we
propose an Tree based interaction mining algorithms to
analyze the structures of the trees[4], so by analyzing the
structure of trees we can extract interaction flow action.
During meetings the human interactionflowisrepresentedin
the form of trees. The advantages of proposed method is The
interaction flow determines the relationship between the
different types of interaction. To understand the content of
meeting mining human interaction is necessary for it. Mining
human interactions performed in two ways
1. The mining result can be used for determining the
meeting content.
2. Secondly, the patterns that are extracted are useful for
understanding interaction betweenthehumansinmeetings.
The extracted patterns are then analyzed and that can be
used to evaluate whether the meeting is in efficient way or
not? And also it is used to compare two meeting discussion.
2. PROCESS FLOW
The interaction issues including turn-taking, gaze
behavior, influence and talkativeness and analyzing user
interactions during poster presentation in an exhibition
room are mainly focus on detecting physical interactions
between participants without anyrelations withtopics[1].
The context used in our interaction detection includes head
motion, notice from others, speech manner, talking time,
and information about previous interaction. Head motion
(e.g. drowsy) is very common and used often in detectionof
human response (acknowledgement or agreement). For
example, when a user is proposing some idea, he is usually
being looked at by most of the participants. Attention from
others can be treated as how many persons looking at the
target user during the interaction. Thus the problem can be
roughly turned into detection of face direction. The face
orientation is determined as the one whose vector makes
the smallest angle. Speech tone refers to whether a
statement is a question or a normal one. Speaking time is
another important indicator in detection the type of human
interaction. The context information is gathered through
multiple sensors e.g. video cameras, microphones, and
motion sensors.

2. International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 04 Issue: 08 | Aug -2017 www.irjet.net p-ISSN: 2395-0072
© 2017, IRJET | Impact Factor value: 5.181 | ISO 9001:2008 Certified Journal | Page 1892
Table -1: A set of Human Interaction
propose A user proposes an idea
with respect to a topic
comment A user gives comments on a
proposal
acknowledgement A user confirms someone
else’s comment or
explanation(eg.yeah,ok)
Request Info A user requests information
about a proposal
When a user puts forward a proposal, it usually takes
relatively long time. But it takes short time when he gives
an acknowledgement or asks a question.
2.1 Pre Processing
1.Stop word removal
2.Stemming (Porter Stemmer Algorithm)
3.Part of speech tagger
Figure 1.preprocessing steps
Figure 2.Block Diagram
2.2 classification
Summary of patterns and corresponding participant
Eg: P1 commented twice, P2 proposed once
Figure 3. Classification Steps
2.3 Pattern Mining
1. Associate the keywords and group them
2. Form a set of patterns PRO-COM, PRO-ACK, PRO
COM- ACK, PRO, PRO-COM-COM-ACK
3. A priori algorithm
Figure 4. Pattern Mining Steps
2.4 Clustering
Behavior of participant identified, if the person’s
Proposal level is high then he will have a passion in the
enhancement of the organization.
Figure 5. Clustering Steps
MODULE
1: PRE-
PROCESS
ING
Key words in the
document
Maintain a Lexicon
Form a set of patterns
Frequent patterns
Text
corpus
Output: Important keywords
Text processing
Stop word removal
stemming
Part of speech tagging
Frequent meeting
pattern
output
K-MEANS CLUSTERING
HUMAN BEHAVIOR
ANALYSIS
Persons are clustered based on
interaction
Most frequent meeting pattern
Using decision tree classifier
Associate the pattern interactions
Group the similar interactions for each participant
Frequent patterns
Identifying dataFeatures selection
Pattern interpretation
and Evaluation
Data
Selection
Preprocessing
for related data
Meeting File
Clustering
classification

3. International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 04 Issue: 08 | Aug -2017 www.irjet.net p-ISSN: 2395-0072
© 2017, IRJET | Impact Factor value: 5.181 | ISO 9001:2008 Certified Journal | Page 1893
3. CONCLUSIONS
we proposed a tree basedminingmethodthatisuseful in
meeting to identify the patterns of human interaction. the
mining result is useful for determining the meeting content,
indexing, comparison of meeting records. This tree based
mining method is valuable to capture various categories of
meetings for analysis such as debate, interview, etc
4. REFERENCES
[1] P. Chiu, A. Kapuskar, S. Reitmeier, and L. Wilcox, “Room
with a Rear View: Meeting Capture in a Multimedia
Conference Room,” IEEE Multimedia, vol. 7, no. 4, pp. 48-54,
Oct.-Dec. 2000.
[2] W. Geyer, H. Richter, and G.D. Abowd, “Towards a
Smarter Meeting Record—Capture and Access of Meetings
Revisited,” Multimedia Tools and Applications, vol. 27, no. 3,
pp. 393-410, 2005.
[3] S. Junuzovic, R. Hegde, Z. Zhang, P. Chou, Z. Liu, and C.
Zhang, “Requirements and Recommendations for an
Enhanced Meeting Viewing Experience,” Proc. ACM Int’l
Conf. Multimedia, pp. 539- 548, 2008.
[4]PalivelaHemant, Prashanth G ,Vijay Kumar S
,KalpanaPatil,¡°Discovering PatternsinInteractions between
Humans and Animals by Using Tree Based Mining¡±
International Journal of Engineering Research&Technology
(IJERT),Vol. 1 Issue 6, August . 2012.
[5] R. Stiefelhagen, J. Yang, and A. Waibel,“ModelingFocusof
Attention for Meeting Indexing Based on Multiple Cues,”
IEEE Trans. Neural Networks, vol.
[6] C. Wang, M. Hong, J. Pei, H. Zhou, W. Wang, and B. Shi,
“EfficientPattern-GrowthMethodsforFrequent TreePattern
Mining,” Proc. Pacific-Asia Conf. Knowledge Discovery and
Data Mining (PAKDD ’04), pp. 441-451, 2004
[7] Q. Yang and X. Wu, “10 Challenging Problems in Data
Mining Research,” Int’l J. Information Technology and
Decision Making, vol. 5, no. 4, pp. 597-604, 2006.
[8] Z. Yu, M. Ozeki, Y. Fujii, andY.Nakamura,“TowardsSmart
Meeting: Enabling Technologies and a Real-World
Application,” Proc. Int’l Conf. Multimodal Interfaces (ICMI
’07), pp. 86-93, 2007.
[9] Z. Yu and Y. Nakamura, “Smart Meeting Systems: A
Survey of State-of-the-Art andOpenIssues,”ACMComputing
Surveys, vol. 42, no. 2, article 8, Feb. 2010.
[10] M.J. Zaki, “Efficiently Mining Frequent Trees ina Forest:
Algorithms and Applications,” IEEE Trans. Knowledge and
Data Eng., vol. 17, no. 8, pp. 1021-1035, Aug. 2005.